@inproceedings{won-etal-2026-trex, title = "{TR}e{X}: Tokenizer Regression for Optimal Data Mixture", author = "Won, Inho and Yoo, Hangyeol and Cho, Minkyung and Park, Jungyeul and Song, Hoyun and Lim, KyungTae", editor = "Demberg, Vera and Inui, Kentaro and Marquez, Llu{\'i}s", booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = mar, year = "2026", address = "Rabat, Morocco", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.298/", pages = "6353--6370", ISBN = "979-8-89176-380-7" }